ETH Zurich - D-INFK - IVC - CVG - People - PhD Students - Sandro Lombardi

Sandro Lombardi

Sandro Lombardi

ETH Zürich
Universitätstrasse 6
CH-8092 Zürich

Department of Computer Science
Computer Vision and Geometry Group
CNB G 100.9

+41 (0)44 63 29 438

About Me

I'm a PhD student at the Computer Vision and Geometry Group of the Institute of Visual Computing at ETH Zurich. My supervisor is Prof. Marc Pollefeys.

I obtained my B.Sc. and M.Sc. degree in Computer Science at ETH Zurich in 2015 and 2017 respectively.

Research Interests

My research interests are diverse. In the past, I've worked on projects involving reconstruction of body parts (e.g. faces or feet), scalable 3D reconstructions from point clouds or human body modelling with deep neural representations. I also advised several thesis projects in related topics, e.g. scene flow and trajectory estimation, point cloud-based reconstruction and meshing algorithms or deep learning-based scene representations for human bodies or objects. Currently, I'm working on scene representations for scene capture and dense reconstruction from dynamic 4D depth videos.

More information can be found on my personal website.

Student Theses

Available Student Projects

Type Title Advisor(s)

Ongoing Student Projects

Type Title Advisor(s)
B DynamicFusion: 3D Reconstruction of Dynamic Scenes Sandro Lombardi

Past Student Projects

Type Title Student Year Advisor(s)
M DeepCrust: Learning to generate Voronoi Seeds for Meshing Matthias Matti SS21 Sandro Lombardi
M Differentiable Meshing of Implicit Neural Representations Mathias Vetsch SS21 Sandro Lombardi,
Martin Oswald
B Curriculum-based Implicit Geometric Regularization for Learning Shapes David Kamm AS20 Sandro Lombardi
M DeepTrajectories: Motion Representation Learning for 4D Reconstruction Livio Steiner AS20 Sandro Lombardi,
Martin Oswald
B ReconRLA: Point-based large-scale Surface Reconstruction from Point Clouds Nicolas Muntwyler AS20 Sandro Lombardi
S D-Hull: Differentiable Convex Hull Soomin Lee AS20 Sandro Lombardi
M Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion in Dynamic 3D Scenes Ivan Tishchenko SS20 Sandro Lombardi,
Martin Oswald
M Learning Continuous Signed Distance Functions for Human Body Yichen Zhang SS20 Zhaopeng Cui,
Sandro Lombardi
S 3D Surface Generation with Tangent Convolutions Parker Ewen SS19 Sandro Lombardi
S Generating 3D Meshes from Point Clouds through Deep Learning Yukun Dai SS19 Sandro Lombardi
M Learning 3D Shapes from Single-View Images Yang Yu SS19 Sandro Lombardi

© CVG, ETH Zürich webmaster: